Method and system for detecting tree obstacle stage of power transmission line

Abstract

The invention discloses a power transmission line tree obstacle stage detection method and system, and relates to the technical field of power transmission line monitoring, and the method comprises the steps: obtaining a zero-sequence current signal and a zero-sequence voltage signal of a power transmission line, determining a corresponding operation state of the power transmission line according to the zero-sequence current signal and the zero-sequence voltage signal, and when the operation state is a grounding fault, carrying out the detection of the tree obstacle stage of the power transmission line; if yes, carrying out characteristic detection on the zero-sequence current signal by adopting a pre-trained zero-sequence characteristic detection model to obtain a corresponding change characteristic, and carrying out tree barrier stage detection on the zero-sequence current signal and the zero-sequence voltage signal according to the change characteristic to obtain a tree barrier stage corresponding to the power transmission line; the technical problems that in the prior art, whether tree obstacles happen to the power transmission line or not is monitored mainly through a remote video monitoring mode, but the method is long in monitoring time consumption, the power transmission line cannot be protected in advance, and the operation reliability of the power transmission line is reduced are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of power transmission line monitoring, and in particular to a method and system for detecting tree obstacle stages of power transmission lines. Background Art

[0002] With the rapid expansion of power grids, the probability of transmission lines crossing densely vegetated areas such as forests and mountains has increased significantly. Managing the safe distance between lines and vegetation has become a core challenge for grid operations and maintenance. Trees growing close to or touching high-voltage conductors can create tree barriers, leading to wildfires and other accidents, seriously threatening the stable operation of the grid.

[0003] Currently, existing technologies mainly rely on remote video monitoring to monitor whether there are tree obstacles on transmission lines. However, this method takes a long time to monitor and cannot provide early protection for transmission lines, which reduces the reliability of transmission line operation. Summary of the Invention

[0004] The present invention provides a method and system for detecting tree obstacles in a transmission line, which solves the technical problem that the existing technology mainly relies on remote video monitoring to monitor whether a transmission line has tree obstacles, but this method takes a long time to monitor, cannot provide early protection for the transmission line, and reduces the reliability of the transmission line operation.

[0005] A first aspect of the present invention provides a method for detecting tree obstacles in a transmission line, comprising:

[0006] Acquire a zero-sequence current signal and a zero-sequence voltage signal of a transmission line, and determine an operating state corresponding to the transmission line according to the zero-sequence current signal and the zero-sequence voltage signal;

[0007] When the operating state is a ground fault, a pre-trained zero-sequence feature detection model is used to perform feature detection on the zero-sequence current signal to obtain corresponding change features;

[0008] A tree barrier stage detection is performed on the zero-sequence current signal and the zero-sequence voltage signal according to the change characteristics to obtain a tree barrier stage corresponding to the transmission line.

[0009] Optionally, the step of determining the operating state corresponding to the transmission line according to the zero-sequence current signal and the zero-sequence voltage signal includes:

[0010] Determining whether the effective current value of the zero-sequence current signal is greater than a preset current threshold;

[0011] If the effective current value is less than or equal to the current threshold, determining the operating state of the transmission line as normal operation;

[0012] If the effective current value is greater than the current threshold, determining whether the effective voltage value of the zero-sequence voltage signal is greater than a preset voltage threshold;

[0013] If the effective voltage value is greater than the voltage threshold, the operating state of the transmission line is determined to be a ground fault;

[0014] If the effective voltage value is less than or equal to the voltage threshold, the operating state of the transmission line is determined to be normal.

[0015] Optionally, the zero-sequence feature detection model includes a wavelet transform layer, a first convolutional network, a second convolutional network, a feature fusion layer, and a change classification head. The step of using the pre-trained zero-sequence feature detection model to perform characteristic detection on the zero-sequence current signal to obtain corresponding change features includes:

[0016] Extracting time-frequency domain features of the zero-sequence current signal through the wavelet transform layer to obtain a time-frequency domain feature map;

[0017] Performing long-term feature extraction on the time-frequency domain feature map through the first convolutional network to obtain a long-term feature map;

[0018] Extracting mutation features from the time-frequency domain feature map using the second convolutional network to obtain a mutation feature map;

[0019] Using a feature fusion layer to perform feature fusion on the long-term feature map and the sudden change feature map to obtain a fused feature map;

[0020] The change classification head is used to perform change feature detection on the fused feature map to obtain corresponding change features.

[0021] Optionally, the second convolutional network includes a deformable convolutional network and a depthwise separable convolutional layer, and the step of extracting mutation features from the time-frequency domain feature map through the second convolutional network to obtain the mutation feature map includes:

[0022] Using a deformable convolutional network to perform a deformable convolution operation on the time-frequency domain feature map to obtain a sudden change waveform feature map;

[0023] The mutation waveform feature map is subjected to feature extraction through a depthwise separable convolutional layer to obtain a mutation feature map.

[0024] Optionally, the step of performing tree barrier stage detection on the zero-sequence current signal and the zero-sequence voltage signal according to the change characteristics to obtain the tree barrier stage corresponding to the transmission line includes:

[0025] performing tree barrier feature extraction on the zero-sequence current signal and the zero-sequence voltage signal to obtain a tree barrier feature value;

[0026] When the change feature is the first change feature, determining whether the tree barrier characteristic value is greater than a preset first stage threshold;

[0027] When the tree barrier characteristic value is greater than the first stage threshold, the initial connection stage is determined as the tree barrier stage corresponding to the transmission line;

[0028] When the change characteristic is the second change characteristic, determining whether the tree barrier characteristic value is greater than a preset second stage threshold;

[0029] When the tree barrier characteristic value is greater than the second stage threshold, the open fire stage is determined as the tree barrier stage corresponding to the transmission line;

[0030] When the change characteristic is the third change characteristic, determining whether the tree barrier characteristic value is greater than a preset third stage threshold;

[0031] When the tree barrier characteristic value is greater than the third stage threshold, the separation stage is determined to be the tree barrier stage corresponding to the transmission line.

[0032] Optionally, the step of performing tree barrier feature extraction on the zero-sequence current signal and the zero-sequence voltage signal to obtain a tree barrier feature value includes:

[0033] Extracting the zero-break moment of the zero-sequence current signal and the peak moment of the zero-sequence voltage signal;

[0034] Calculating the phase difference between each of the zero-rest moments and the associated peak moment to obtain a plurality of phase differences;

[0035] performing absolute value processing on each of the phase differences to obtain a plurality of first absolute values;

[0036] respectively determining whether each of the first absolute values ​​is within a preset tree obstacle interval;

[0037] When the first absolute value is within the tree barrier interval, determining the first absolute value as an initial tree barrier characteristic value;

[0038] The number of all the initial tree barrier characteristic values ​​is counted, and the number is used as the tree barrier characteristic value.

[0039] A second aspect of the present invention provides a transmission line tree obstacle detection system, comprising:

[0040] an acquisition module, configured to acquire a zero-sequence current signal and a zero-sequence voltage signal of a transmission line, and determine an operating state corresponding to the transmission line according to the zero-sequence current signal and the zero-sequence voltage signal;

[0041] a feature detection module, configured to, when the operating state is a ground fault, use a pre-trained zero-sequence feature detection model to perform feature detection on the zero-sequence current signal to obtain corresponding change features;

[0042] The tree barrier stage detection module is used to perform tree barrier stage detection on the zero-sequence current signal and the zero-sequence voltage signal according to the change characteristics to obtain the tree barrier stage corresponding to the transmission line.

[0043] A third aspect of the present invention provides an electronic device comprising a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the transmission line tree barrier stage detection method as described in any one of the above items.

[0044] A fourth aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed, implements the method for detecting tree obstacles in a transmission line as described in any one of the above items.

[0045] A fifth aspect of the present invention provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions, wherein when the program instructions are executed by a computer, the computer executes the transmission line tree barrier stage detection method as described in any one of the above items.

[0046] It can be seen from the above technical solutions that the present invention has the following advantages:

[0047] The present invention obtains the zero-sequence current and zero-sequence voltage signals of a transmission line and determines the corresponding operating state of the transmission line based on these signals. When the operating state is a ground fault, a pre-trained zero-sequence feature detection model is used to detect the characteristics of the zero-sequence current signal to obtain the corresponding change characteristics. Based on the change characteristics, the zero-sequence current and zero-sequence voltage signals are then used to perform tree barrier detection to determine the corresponding tree barrier stage of the transmission line. This overcomes the technical problem that the existing technology relies primarily on remote video monitoring to monitor whether a transmission line has experienced a tree barrier, but this method is time-consuming, cannot provide early protection for the transmission line, and reduces the reliability of the transmission line operation. Compared with traditional tree barrier detection methods for transmission lines, the present invention uses a zero-sequence feature detection model to extract the change characteristics of the zero-sequence current signal and performs tree barrier detection on the zero-sequence current and zero-sequence voltage signals based on the change characteristics to determine the corresponding tree barrier stage of the transmission line. This allows operation and maintenance personnel to protect the transmission line at the early stages of a tree barrier, thereby improving the reliability of the transmission line operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0049] Figure 1 A flowchart of a method for detecting tree obstacles in a transmission line according to the first embodiment of the present invention;

[0050] Figure 2 A flowchart of a method for detecting tree obstacles in a transmission line according to a second embodiment of the present invention;

[0051] Figure 3 A schematic diagram of the structure of a zero-sequence feature detection model provided in the second embodiment of the present invention;

[0052] Figure 4 This is a structural block diagram of a power transmission line tree obstacle detection system provided in the third embodiment of the present invention;

[0053] Figure 5 This is a structural block diagram of a computer device provided in Example 4 of the present invention. DETAILED DESCRIPTION

[0054] The embodiments of the present invention provide a method and system for detecting tree barriers in a transmission line, which are used to solve the technical problem that the existing technology mainly relies on remote video monitoring to monitor whether a transmission line has tree barriers. However, this method takes a long time to monitor and cannot provide early protection for the transmission line, thereby reducing the reliability of the transmission line operation.

[0055] In order to make the purpose, features, and advantages of the present invention more obvious and easy to understand, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described below are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0056] See also Figure 1 , Figure 1 This is a flowchart of the steps of a method for detecting tree obstacles in a transmission line provided in the first embodiment of the present invention.

[0057] The present invention provides a method for detecting tree obstacles in a transmission line, comprising:

[0058] Step 101: Acquire a zero-sequence current signal and a zero-sequence voltage signal of a transmission line, and determine a corresponding operating state of the transmission line according to the zero-sequence current signal and the zero-sequence voltage signal.

[0059] The zero-sequence current signal refers to the in-phase component of the three-phase current of the transmission line.

[0060] The zero-sequence voltage signal refers to the in-phase component of the three-phase voltage of the transmission line.

[0061] The operating status refers to the operating status of the transmission line, which includes normal operation and ground fault.

[0062] In an embodiment of the present invention, a zero-sequence current signal and a zero-sequence voltage signal of a transmission line are obtained by a preset monitoring device, and it is determined whether the effective current value of the zero-sequence current signal is greater than a preset current threshold value. If the effective current value is less than or equal to the current threshold value, the operating state of the transmission line is determined to be normal operation. If the effective current value is greater than the current threshold value, it is determined whether the effective voltage value of the zero-sequence voltage signal is greater than a preset voltage threshold value. If the effective voltage value is greater than the voltage threshold value, the operating state of the transmission line is determined to be a ground fault. If the effective voltage value is less than or equal to the voltage threshold value, the operating state of the transmission line is determined to be normal operation.

[0063] It should be noted that the monitoring equipment includes a voltage transformer and a current transformer, and the zero-sequence voltage signal of the transmission line is obtained through the voltage transformer, and the zero-sequence current signal of the transmission line is obtained through the current transformer.

[0064] Step 102: When the operating state is a ground fault, a pre-trained zero-sequence feature detection model is used to perform feature detection on the zero-sequence current signal to obtain corresponding change features.

[0065] Variation characteristics refer to the waveform characteristics of the zero-sequence current signal. They include but are not limited to the first variation characteristic (i.e., the amplitude or phase of the zero-sequence current waveform fluctuates dramatically), the second variation characteristic (i.e., the zero-sequence current waveform changes slowly and continuously), and the third variation characteristic (i.e., the zero-sequence current waveform changes slowly and continuously and then remains zero).

[0066] In this embodiment of the present invention, when the operating state is a ground fault, a pre-trained zero-sequence feature detection model is used to detect the characteristics of the zero-sequence current signal and obtain the corresponding change characteristics. The zero-sequence feature detection model includes a wavelet transform layer, a first convolutional network, a second convolutional network, a feature fusion layer, and a change classification head.

[0067] It is worth mentioning that the zero-sequence feature detection model is specifically as follows: A1. Acquire multiple tree barrier zero-sequence current signals, and pre-process each tree barrier zero-sequence current signal to obtain a training feature set. A2. Use the training feature set to input the preset initial zero-sequence feature detection model for training, and output the training change feature. A3. Based on the preset training loss function, calculate the training loss function value of the training feature set according to the training change feature, wherein the training loss function includes but is not limited to the focal loss function and the Huber loss function. A4. When the training loss function value is greater than or equal to the preset standard loss function value, use the grid search method or the random search method to adjust the network parameters of the initial zero-sequence feature detection model until the training loss function value is less than the standard loss function value. A5. When the training loss function value is less than the standard loss function value, generate a zero-sequence feature detection model.

[0068] Step 103: Perform tree barrier stage detection on the zero-sequence current signal and the zero-sequence voltage signal according to the change characteristics to obtain the tree barrier stage corresponding to the transmission line.

[0069] The tree barrier stage refers to the dynamic development process of a ground fault on a transmission line caused by trees contacting the conductors, including but not limited to the initial connection stage, the open fire stage and the separation stage.

[0070] In an embodiment of the present invention, tree barrier features are extracted from the zero-sequence current signal and the zero-sequence voltage signal to obtain a tree barrier feature value. When the change feature is the first change feature, it is determined whether the tree barrier feature value is greater than a preset first-stage threshold. When the tree barrier feature value is greater than the first-stage threshold, the initial connection stage is determined as the tree barrier stage corresponding to the transmission line. When the change feature is the second change feature, it is determined whether the tree barrier feature value is greater than the preset second-stage threshold. When the tree barrier feature value is greater than the second-stage threshold, the open fire stage is determined as the tree barrier stage corresponding to the transmission line. When the change feature is the third change feature, it is determined whether the tree barrier feature value is greater than the preset third-stage threshold. When the tree barrier feature value is greater than the third-stage threshold, the separation stage is determined as the tree barrier stage corresponding to the transmission line.

[0071] In an embodiment of the present invention, the zero-sequence current signal and zero-sequence voltage signal of a transmission line are acquired, and the corresponding operating state of the transmission line is determined based on the zero-sequence current and zero-sequence voltage signals. When the operating state is a ground fault, a pre-trained zero-sequence feature detection model is used to perform characteristic detection on the zero-sequence current signal to obtain corresponding variation characteristics. Based on the variation characteristics, a tree barrier stage detection is performed on the zero-sequence current and zero-sequence voltage signals to determine the corresponding tree barrier stage of the transmission line. This overcomes the technical problem that the prior art relies primarily on remote video monitoring to monitor transmission lines for tree barrier conditions, but this method is time-consuming, cannot provide early protection for the transmission line, and reduces the reliability of transmission line operation. Compared with traditional tree barrier detection methods for transmission lines, the present invention uses a zero-sequence feature detection model to extract the variation characteristics of the zero-sequence current signal, and based on the variation characteristics, performs tree barrier stage detection on the zero-sequence current and zero-sequence voltage signals to determine the corresponding tree barrier stage of the transmission line. This allows operation and maintenance personnel to protect the transmission line at the early stages of a tree barrier, thereby improving the reliability of transmission line operation.

[0072] See also Figure 2 , Figure 2 This is a flowchart of the steps of a method for detecting tree obstacles in a transmission line provided in the second embodiment of the present invention.

[0073] The present invention provides a method for detecting tree obstacles in a transmission line, comprising:

[0074] Step 201: Acquire a zero-sequence current signal and a zero-sequence voltage signal of a transmission line, and determine a corresponding operating state of the transmission line according to the zero-sequence current signal and the zero-sequence voltage signal.

[0075] Furthermore, step 201 includes the following sub-steps:

[0076] S11. Determine whether the effective current value of the zero-sequence current signal is greater than a preset current threshold.

[0077] The current threshold refers to the critical current value used to determine whether a ground fault occurs in a transmission line.

[0078] In an embodiment of the present invention, the effective current value of the zero-sequence current signal is calculated, and it is determined whether the effective current value is greater than a preset current threshold.

[0079] It should be noted that the expression of the effective value of current is specifically:

[0080]

[0081] in, is the effective value of current, is the signal width (i.e. the window width for collecting signals), is the instantaneous value of zero-sequence current at the kth moment, is the sampling time.

[0082] S12. If the effective current value is less than or equal to the current threshold, the operating state of the transmission line is determined to be normal.

[0083] In the embodiment of the present invention, when the effective current value is less than or equal to the current threshold, it is determined that the transmission line is operating normally, and the operating state of the transmission line is determined to be operating normally.

[0084] S13. If the effective current value is greater than the current threshold, determine whether the effective voltage value of the zero-sequence voltage signal is greater than a preset voltage threshold.

[0085] The voltage threshold refers to the critical voltage value used to determine whether a ground fault occurs in a transmission line.

[0086] In an embodiment of the present invention, when the effective current value is greater than the current threshold, the effective voltage value of the zero-sequence voltage signal is calculated to determine whether the effective voltage value is greater than a preset voltage threshold.

[0087] It should be noted that the specific expression of the voltage efficiency value is:

[0088]

[0089] in, is the voltage efficiency value, is the instantaneous value of the zero-sequence voltage at the kth moment.

[0090] S14. If the effective voltage value is greater than the voltage threshold, the operating state of the transmission line is determined to be a ground fault.

[0091] In the embodiment of the present invention, when the effective value of the voltage is greater than the voltage threshold, it is determined that a ground fault occurs in the transmission line, and the operating state of the transmission line is determined to be a ground fault.

[0092] S15. If the effective voltage value is less than or equal to the voltage threshold, the operating state of the transmission line is determined to be normal.

[0093] In the embodiment of the present invention, when the effective voltage value is less than or equal to the voltage threshold, it is determined that no ground fault occurs in the transmission line, and the operation state of the transmission line is determined to be normal.

[0094] Step 202: When the operating state is a ground fault, a pre-trained zero-sequence feature detection model is used to perform feature detection on the zero-sequence current signal to obtain corresponding change features.

[0095] Further, see Figure 3As shown, the zero-sequence feature detection model includes a wavelet transform layer, a first convolutional network, a second convolutional network, a feature fusion layer and a change classification head. Step 202 includes the following sub-steps:

[0096] S21. Extract the time-frequency domain features of the zero-sequence current signal through the wavelet transform layer to obtain a time-frequency domain feature map.

[0097] The time-frequency domain characteristic diagram refers to the time-frequency characteristics in the zero-sequence current signal.

[0098] In the embodiment of the present invention, a wavelet transform layer is used to extract the time-frequency domain features of the zero-sequence current signal to obtain a time-frequency domain feature map.

[0099] It should be noted that the wavelet transform layer is a hybrid structure that embeds wavelet analysis into a neural network. Its core function is to decompose the time-frequency characteristics of the input signal through filter banks of different scales and reduce data redundancy by using the energy compression characteristics of wavelets.

[0100] S22. Perform long-term feature extraction on the time-frequency domain feature map through the first convolutional network to obtain a long-term feature map.

[0101] The long-term feature map refers to the slowly changing trend characteristics of the time-frequency domain feature map.

[0102] It should be noted that, see Figure 3 As shown, the first convolutional network refers to the temporal convolutional network.

[0103] In an embodiment of the present invention, a temporal convolutional network is used to extract long-term features from a time-frequency domain feature map to obtain a long-term feature map.

[0104] S23. Extract mutation features from the time-frequency domain feature map through a second convolutional network to obtain a mutation feature map.

[0105] Further, see Figure 3 As shown, the second convolutional network includes a deformable convolutional network and a depth-wise separable convolutional layer, and S23 includes the following sub-steps:

[0106] S231. Use a deformable convolution network to perform a deformable convolution operation on the time-frequency domain feature map to obtain a mutation waveform feature map.

[0107] The mutation waveform feature graph refers to the mutation characteristics of the time-frequency domain feature graph.

[0108] In an embodiment of the present invention, a deformable convolutional network is used to extract mutation features of a time-frequency domain feature graph to obtain a mutation waveform feature graph.

[0109] It should be noted that the deformable convolutional network is an improved traditional convolutional neural network. By introducing a learnable spatial sampling position offset, the convolution kernel can dynamically adapt to the geometric deformation or complex spatial layout of the target, significantly improving the model's ability to model irregular shapes (such as object occlusion, perspective changes, etc.).

[0110] S232. Extract features from the mutation waveform feature map through a depthwise separable convolutional layer to obtain a mutation feature map.

[0111] In an embodiment of the present invention, a depthwise separable convolutional layer is used to extract features from a mutation waveform feature map to obtain a mutation feature map.

[0112] S24. Use a feature fusion layer to fuse the long-term feature map and the mutation feature map to obtain a fused feature map.

[0113] In an embodiment of the present invention, a long-term feature map and a sudden change feature map are spliced ​​together through a feature fusion layer to obtain a fused feature map.

[0114] S25. Use the change classification head to detect change features on the fused feature map to obtain corresponding change features.

[0115] In an embodiment of the present invention, a change classification head is used to detect change features on the fused feature map to obtain corresponding change features, wherein the change classification head includes a fully connected layer and a Softmax activation function layer (i.e., a normalized exponential layer) connected in sequence.

[0116] Step 203: extract tree barrier features from the zero-sequence current signal and the zero-sequence voltage signal to obtain tree barrier feature values.

[0117] Furthermore, step 203 includes the following sub-steps:

[0118] S31. Extracting the zero-break moment of the zero-sequence current signal and the peak moment of the zero-sequence voltage signal.

[0119] The zero-off moment refers to the special moment when a brief interruption or return to zero occurs in the zero-sequence current signal.

[0120] The peak moment refers to the time point when the zero-sequence voltage signal reaches the local maximum value (peak value).

[0121] In an embodiment of the present invention, the zero-off time of the zero-sequence current signal and the peak time of the zero-sequence voltage signal are extracted. For example, by determining whether the absolute value of the instantaneous zero-sequence current value at each moment is less than 0.05, the moment is determined to be the zero-off time when the absolute value of the instantaneous zero-sequence current value is less than 0.05. The peak time of the zero-sequence voltage signal is extracted using a preset sliding window.

[0122] S32. Calculate the phase difference between each zero-rest moment and the associated peak moment to obtain multiple phase differences.

[0123] S33, performing absolute value processing on each phase difference to obtain multiple first absolute values;

[0124] S34, respectively determining whether each first absolute value is within a preset tree obstacle interval;

[0125] S35. When the first absolute value is in the tree barrier interval, the first absolute value is determined as the initial tree barrier characteristic value.

[0126] The tree barrier interval refers to the phase difference between the zero-off time and the associated peak time when a tree-to-ground fault occurs on a transmission line. The value is [90° - B, 90° + B], where B is the error value and can be set based on historical transmission current data.

[0127] The initial tree barrier characteristic value refers to the first absolute value in the tree barrier interval.

[0128] In this embodiment of the present invention, the phase difference between each zero-rest moment and the associated peak moment is calculated to obtain multiple phase differences. The absolute value of each phase difference is calculated to obtain multiple first absolute values. A determination is made as to whether each first absolute value is within the range [90°-B, 90°+B]. When the first absolute value is within the range [90°-B, 90°+B], the first absolute value is determined as the initial tree barrier characteristic value.

[0129] S36. Count the number of all initial tree barrier characteristic values, and use the number as the tree barrier characteristic value.

[0130] The tree barrier characteristic value refers to the total number of initial tree barrier characteristic values.

[0131] In the embodiment of the present invention, the number of initial tree barrier characteristic values ​​is counted and used as the tree barrier characteristic value.

[0132] Step 204: When the change characteristic is the first change characteristic, determine whether the tree barrier characteristic value is greater than a preset first stage threshold.

[0133] The first change characteristic refers to the sharp fluctuation of the amplitude or phase of the zero-sequence current waveform.

[0134] The first stage threshold refers to the critical value used to determine whether the transmission line is in the initial connection stage.

[0135] In the embodiment of the present invention, when the variation characteristic is the first variation characteristic (ie, a sharp fluctuation in amplitude or phase occurs in the zero-sequence current signal), it is determined that the tree barrier characteristic value speed is greater than a preset first stage threshold.

[0136] Step 205: When the tree barrier characteristic value is greater than the first stage threshold, the initial connection stage is determined as the tree barrier stage corresponding to the transmission line.

[0137] The initial connection stage refers to the initial stage of a tree-to-wire grounding fault in a transmission line. The core feature is the instantaneous electrical signal mutation caused by the initial contact between the tree and the conductor.

[0138] In an embodiment of the present invention, if the tree barrier characteristic value is greater than the first stage threshold, it is determined that the transmission line is in the initial stage of a tree-on-line grounding fault, and the initial connection stage is determined as the tree barrier stage corresponding to the transmission line.

[0139] It should be noted that when the tree barrier characteristic value is less than or equal to the first stage threshold, it is determined that the transmission line is grounded.

[0140] Step 206: When the change characteristic is the second change characteristic, determine whether the tree barrier characteristic value is greater than a preset second stage threshold.

[0141] The second change characteristic refers to the continuous slow change of the zero-sequence current waveform.

[0142] The second stage threshold refers to the critical value for determining whether the transmission line is in the open flame stage.

[0143] In the embodiment of the present invention, when the variation characteristic is the second variation characteristic (ie, the instantaneous value of the zero-sequence current signal varies continuously and slowly), it is determined whether the tree barrier characteristic value is greater than a preset second stage threshold.

[0144] Step 207: When the tree barrier characteristic value is greater than the second stage threshold, the open fire stage is determined as the tree barrier stage corresponding to the transmission line.

[0145] The open flame stage refers to the mid-stage of the development of a tree-to-wire grounding fault on a transmission line. Its core feature is the continuous contact between trees and conductors, which triggers stable arc discharge.

[0146] In the embodiment of the present invention, when the tree barrier characteristic value is greater than the second stage threshold, it is determined that the transmission line is in the middle stage of the tree-on-line grounding fault development, and the open fire stage is determined as the tree barrier stage corresponding to the transmission line.

[0147] It should be noted that when the tree barrier characteristic value is less than or equal to the second stage threshold, it is determined that the transmission line is grounded.

[0148] Step 208: When the change characteristic is the third change characteristic, determine whether the tree barrier characteristic value is greater than a preset third stage threshold.

[0149] The third change characteristic refers to the fact that the zero-sequence current waveform continues to change slowly and then remains at zero.

[0150] The third stage threshold refers to the critical value for determining whether the transmission line is in the separation stage.

[0151] In an embodiment of the present invention, when the change characteristic is the third change characteristic (ie, the instantaneous value of the zero-sequence current signal changes slowly and then remains zero), it is determined whether the tree barrier characteristic value is greater than a preset third stage threshold.

[0152] Step 209: When the tree barrier characteristic value is greater than the third stage threshold, the separation stage is determined to be the tree barrier stage corresponding to the transmission line.

[0153] The separation stage refers to the final stage of the development of a tree-to-wire grounding fault on a transmission line. The core feature is that the tree and the conductor are completely separated due to arc burning or external force, and the fault disappears on its own.

[0154] In an embodiment of the present invention, when the tree barrier characteristic value is greater than the preset third stage threshold, it is determined that the transmission line is in the final stage of the tree-on-line grounding fault development, and the separation stage is determined as the tree barrier stage corresponding to the transmission line.

[0155] It should be noted that when the tree barrier characteristic value is less than or equal to the preset third stage threshold, it is determined that the transmission line is grounded.

[0156] In an embodiment of the present invention, the zero-sequence current signal and zero-sequence voltage signal of a transmission line are acquired, and the corresponding operating state of the transmission line is determined based on the zero-sequence current and zero-sequence voltage signals. When the operating state is a ground fault, a pre-trained zero-sequence feature detection model is used to perform characteristic detection on the zero-sequence current signal to obtain corresponding variation characteristics. Based on the variation characteristics, a tree barrier stage detection is performed on the zero-sequence current and zero-sequence voltage signals to determine the corresponding tree barrier stage of the transmission line. This overcomes the technical problem that the prior art relies primarily on remote video monitoring to monitor transmission lines for tree barrier conditions, but this method is time-consuming, cannot provide early protection for the transmission line, and reduces the reliability of transmission line operation. Compared with traditional tree barrier detection methods for transmission lines, the present invention uses a zero-sequence feature detection model to extract the variation characteristics of the zero-sequence current signal, and based on the variation characteristics, performs tree barrier stage detection on the zero-sequence current and zero-sequence voltage signals to determine the corresponding tree barrier stage of the transmission line. This allows operation and maintenance personnel to protect the transmission line at the early stages of a tree barrier, thereby improving the reliability of transmission line operation.

[0157] See also Figure 4 , Figure 4 This is a structural block diagram of a transmission line tree obstacle detection system provided in the third embodiment of the present invention.

[0158] The present invention provides a transmission line tree obstacle detection system, comprising:

[0159] An acquisition module 301 is configured to acquire a zero-sequence current signal and a zero-sequence voltage signal of a transmission line, and determine an operating state of the transmission line according to the zero-sequence current signal and the zero-sequence voltage signal;

[0160] The feature detection module 302 is used to detect the characteristics of the zero-sequence current signal using a pre-trained zero-sequence feature detection model to obtain corresponding change characteristics when the operating state is a ground fault;

[0161] The tree barrier stage detection module 303 is used to perform tree barrier stage detection on the zero-sequence current signal and the zero-sequence voltage signal according to the change characteristics, and obtain the tree barrier stage corresponding to the transmission line.

[0162] Furthermore, the acquisition module 301 includes:

[0163] The first analysis submodule is used to determine whether the effective current value of the zero-sequence current signal is greater than a preset current threshold;

[0164] If the effective current value is less than or equal to the current threshold, the operation state of the transmission line is determined to be normal;

[0165] The second analysis submodule is configured to determine whether the voltage effective value of the zero-sequence voltage signal is greater than a preset voltage threshold if the current effective value is greater than the current threshold;

[0166] If the effective value of the voltage is greater than the voltage threshold, the operating state of the transmission line determines that a ground fault has occurred;

[0167] If the effective voltage value is less than or equal to the voltage threshold, the operating state of the transmission line is determined to be normal.

[0168] Furthermore, the zero-sequence feature detection model includes a wavelet transform layer, a first convolutional network, a second convolutional network, a feature fusion layer, and a change classification head. The feature detection module 302 includes:

[0169] The wavelet transform submodule is used to extract the time-frequency domain features of the zero-sequence current signal through the wavelet transform layer to obtain the time-frequency domain feature map;

[0170] A long-term feature extraction submodule is used to extract long-term features from the time-frequency domain feature map through the first convolutional network to obtain a long-term feature map;

[0171] The mutation feature extraction submodule is used to extract mutation features from the time-frequency domain feature map through the second convolutional network to obtain a mutation feature map;

[0172] The splicing submodule is used to fuse the long-term feature map and the mutation feature map using the feature fusion layer to obtain a fused feature map;

[0173] The detection submodule is used to detect the change features of the fused feature map using the change classification head to obtain the corresponding change features.

[0174] Furthermore, the second convolutional network includes a deformable convolutional network and a depthwise separable convolutional layer, and a mutation feature extraction submodule, including:

[0175] A convolution operation unit, configured to perform a deformable convolution operation on the time-frequency domain feature map using a deformable convolution network to obtain a mutation waveform feature map;

[0176] The feature extraction unit is used to extract features from the mutation waveform feature map through a depth-wise separable convolutional layer to obtain a mutation feature map.

[0177] Furthermore, the tree obstacle detection module 303 includes:

[0178] The tree barrier feature calculation submodule is used to extract the tree barrier features from the zero-sequence current signal and the zero-sequence voltage signal to obtain the tree barrier feature value;

[0179] The third analysis submodule is configured to determine whether the tree barrier characteristic value is greater than a preset first stage threshold when the change characteristic is the first change characteristic;

[0180] When the tree barrier characteristic value is greater than the first stage threshold, the initial overlap stage is determined as the tree barrier stage corresponding to the transmission line;

[0181] When the change feature is the second change feature, it is determined whether the tree barrier feature value is greater than the preset second stage threshold;

[0182] When the tree barrier characteristic value is greater than the second stage threshold, the open fire stage is determined as the tree barrier stage corresponding to the transmission line;

[0183] When the change characteristic is the third change characteristic, it is determined whether the tree barrier characteristic value is greater than the preset third stage threshold;

[0184] When the tree barrier characteristic value is greater than the third stage threshold, the separation stage is determined to be the tree barrier stage corresponding to the transmission line.

[0185] Furthermore, the tree obstacle feature calculation submodule includes:

[0186] An extraction unit, used to extract the zero-break moment of the zero-sequence current signal and the peak moment of the zero-sequence voltage signal;

[0187] A phase difference unit is used to calculate the phase difference between each zero-rest moment and the associated peak moment to obtain multiple phase differences;

[0188] an analyzing unit, configured to perform absolute value processing on each phase difference to obtain a plurality of first absolute values;

[0189] respectively determining whether each first absolute value is within a preset tree obstacle interval;

[0190] When the first absolute value is in the tree barrier interval, the first absolute value is determined as the initial tree barrier characteristic value;

[0191] Count the number of all initial tree barrier characteristic values ​​and use the number as the tree barrier characteristic value.

[0192] See also Figure 5 , Figure 5 This is a structural block diagram of a computer device provided in Example 4 of the present invention.

[0193] An electronic device according to an embodiment of the present invention includes: a memory 401 and a processor 402, wherein the memory 401 stores a computer program; when the computer program is executed by the processor 402, the processor 402 executes the power transmission line tree obstacle stage detection method as described in any of the above embodiments.

[0194] Memory 401 may be an electronic memory such as flash memory, EEPROM (Electrically Erasable Programmable Read-Only Memory), EPROM, hard disk, or ROM. Memory 401 has storage space 403 for program code 413 for executing any of the method steps described above. For example, storage space 403 for program code may include individual program codes 413 for implementing various steps in the method described above. These program codes may be read from or written to one or more computer program products. These computer program products include program code carriers such as hard disks, compact disks (CDs), memory cards, or floppy disks. The program codes may be compressed, for example, in a suitable format. When executed by a processing device, these codes cause the processing device to execute the various steps in the method described above. These program codes may be read from or written to one or more computer program products. These computer program products include program code carriers such as hard disks, compact disks (CDs), memory cards, or floppy disks. The program codes may be compressed, for example, in a suitable format. When these codes are executed by a computing and processing device, the computing and processing device is caused to execute the various steps of the above-described method for detecting tree obstacles in a transmission line.

[0195] The fifth embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method for detecting tree obstacles in a transmission line according to any of the above embodiments is implemented.

[0196] Embodiment 6 of the present invention further provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer executes the transmission line tree barrier stage detection method as described in any of the above embodiments.

[0197] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0198] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0199] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0200] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0201] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the various embodiments of the method of the present invention. The aforementioned storage medium includes various media that can store program code, such as USB flash drives, mobile hard drives, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical disks.

[0202] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A method for detecting tree obstacles in a transmission line, characterized in that: include: Acquire a zero-sequence current signal and a zero-sequence voltage signal of a transmission line, and determine an operating state corresponding to the transmission line according to the zero-sequence current signal and the zero-sequence voltage signal; When the operating state is a ground fault, a pre-trained zero-sequence feature detection model is used to perform feature detection on the zero-sequence current signal to obtain corresponding change features; A tree barrier stage detection is performed on the zero-sequence current signal and the zero-sequence voltage signal according to the change characteristics to obtain a tree barrier stage corresponding to the transmission line.

2. The method for detecting tree obstacles in a transmission line according to claim 1, characterized in that: The step of determining the operating state corresponding to the transmission line according to the zero-sequence current signal and the zero-sequence voltage signal comprises: Determining whether the effective current value of the zero-sequence current signal is greater than a preset current threshold; If the effective current value is less than or equal to the current threshold, determining the operating state of the transmission line as normal operation; If the effective current value is greater than the current threshold, determining whether the effective voltage value of the zero-sequence voltage signal is greater than a preset voltage threshold; If the effective voltage value is greater than the voltage threshold, the operating state of the transmission line is determined to be a ground fault; If the effective voltage value is less than or equal to the voltage threshold, the operating state of the transmission line is determined to be normal.

3. The method for detecting tree obstacles in a transmission line according to claim 1, characterized in that: The zero-sequence feature detection model includes a wavelet transform layer, a first convolutional network, a second convolutional network, a feature fusion layer, and a change classification head. The step of using the pre-trained zero-sequence feature detection model to perform characteristic detection on the zero-sequence current signal to obtain corresponding change features includes: Extracting time-frequency domain features of the zero-sequence current signal through the wavelet transform layer to obtain a time-frequency domain feature map; Performing long-term feature extraction on the time-frequency domain feature map through the first convolutional network to obtain a long-term feature map; Extracting mutation features from the time-frequency domain feature map using the second convolutional network to obtain a mutation feature map; Using a feature fusion layer to perform feature fusion on the long-term feature map and the sudden change feature map to obtain a fused feature map; The change classification head is used to perform change feature detection on the fused feature map to obtain corresponding change features.

4. The method for detecting tree obstacles in a power transmission line according to claim 3, characterized in that: The second convolutional network includes a deformable convolutional network and a depthwise separable convolutional layer. The step of extracting mutation features from the time-frequency domain feature map through the second convolutional network to obtain a mutation feature map includes: Using a deformable convolutional network to perform a deformable convolution operation on the time-frequency domain feature map to obtain a sudden change waveform feature map; The mutation waveform feature map is subjected to feature extraction through a depthwise separable convolutional layer to obtain a mutation feature map.

5. The method for detecting tree obstacles in a transmission line according to claim 1, characterized in that: The step of performing tree barrier stage detection on the zero-sequence current signal and the zero-sequence voltage signal according to the change characteristics to obtain the tree barrier stage corresponding to the transmission line includes: performing tree barrier feature extraction on the zero-sequence current signal and the zero-sequence voltage signal to obtain a tree barrier feature value; When the change feature is the first change feature, determining whether the tree barrier characteristic value is greater than a preset first stage threshold; When the tree barrier characteristic value is greater than the first stage threshold, the initial connection stage is determined as the tree barrier stage corresponding to the transmission line; When the change characteristic is the second change characteristic, determining whether the tree barrier characteristic value is greater than a preset second stage threshold; When the tree barrier characteristic value is greater than the second stage threshold, the open fire stage is determined as the tree barrier stage corresponding to the transmission line; When the change characteristic is the third change characteristic, determining whether the tree barrier characteristic value is greater than a preset third stage threshold; When the tree barrier characteristic value is greater than the third stage threshold, the separation stage is determined to be the tree barrier stage corresponding to the transmission line.

6. The method for detecting tree obstacles in a transmission line according to claim 5, characterized in that: The step of performing tree barrier feature extraction on the zero-sequence current signal and the zero-sequence voltage signal to obtain a tree barrier feature value includes: Extracting the zero-break moment of the zero-sequence current signal and the peak moment of the zero-sequence voltage signal; Calculating the phase difference between each of the zero-rest moments and the associated peak moment to obtain a plurality of phase differences; performing absolute value processing on each of the phase differences to obtain a plurality of first absolute values; respectively determining whether each of the first absolute values ​​is within a preset tree obstacle interval; When the first absolute value is within the tree barrier interval, determining the first absolute value as an initial tree barrier characteristic value; The number of all the initial tree barrier characteristic values ​​is counted, and the number is used as the tree barrier characteristic value.

7. A power transmission line tree obstacle detection system, characterized in that: include: an acquisition module, configured to acquire a zero-sequence current signal and a zero-sequence voltage signal of a transmission line, and determine an operating state corresponding to the transmission line according to the zero-sequence current signal and the zero-sequence voltage signal; a feature detection module, configured to, when the operating state is a ground fault, use a pre-trained zero-sequence feature detection model to perform feature detection on the zero-sequence current signal to obtain corresponding change features; The tree barrier stage detection module is used to perform tree barrier stage detection on the zero-sequence current signal and the zero-sequence voltage signal according to the change characteristics to obtain the tree barrier stage corresponding to the transmission line.

8. An electronic device, characterized in that: The method comprises a memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the processor executes the steps of the method for detecting tree obstacles in a transmission line according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed, the method for detecting tree obstacles in a transmission line according to any one of claims 1 to 6 is implemented.

10. A computer program product, characterized in that The computer program product includes a computer program stored on a non-transitory computer-readable storage medium, wherein the computer program includes program instructions, wherein when the program instructions are executed by a computer, the computer is caused to execute the transmission line tree obstacle stage detection method according to any one of claims 1 to 6.

Images